REVIEW 2 cited by
Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Although it is well known that exploration plays a key role in Reinforcement Learning (RL), prevailing exploration strategies for continuous control tasks in RL are mainly based on naive isotropic Gaussian noise regardless of the causality relationship between action space and the task and consider all dimensions of actions equally important. In this work, we propose to conduct interventions on the primal action space to discover the causal relationship between the action space and the task reward. We propose the method of State-Wise Action Refined (SWAR), which addresses the issue of action space redundancy and promote causality discovery in RL. We formulate causality discovery in RL tasks as a state-dependent action space selection problem and propose two practical algorithms as solutions. The first approach, TD-SWAR, detects task-related actions during temporal difference learning, while the second approach, Dyn-SWAR, reveals important actions through dynamic model prediction. Empirically, both methods provide approaches to understand the decisions made by RL agents and improve learning efficiency in action-redundant tasks.
Forward citations
Cited by 2 Pith papers
-
Property-driven Causal Abstractions for Markov Decision Processes
Property-driven feature causes on factored MDPs yield small abstractions (MDP/IMDP/SG) that often preserve near-optimal policies and can transfer to larger model variants.
-
AutoIndexer: A Reinforcement Learning-Enhanced Index Advisor Towards Scaling Workloads
AutoIndexer combines workload compression with a state-wise reinforcement learning agent and reports up to 95% runtime reduction versus no indexes and roughly 20% better cost savings than prior RL advisors.
Discussion (0). Continue with ORCID to comment.